一键导入
storybrand-messaging-framework
Use StoryBrand for "clarify my message", "rewrite my homepage", "create a BrandScript", "what is my one-liner", or "fix my CTA".
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use StoryBrand for "clarify my message", "rewrite my homepage", "create a BrandScript", "what is my one-liner", or "fix my CTA".
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Harness Engineering 第一阶段:扫描现有项目,生成 AGENTS.md(目录文件)和完整的 docs/ 知识库结构。 当用户想要"为项目添加 agent 支持"、"让 AI 更好地理解我的项目"、"开始 harness engineering"、 "创建 AGENTS.md"、"搭建 agent 文档结构"、"让 Claude Code 更好地工作"时,立即使用此 skill。 也适用于用户说"帮我把项目文档整理好给 agent 用"、"我想开始用 AI agent 开发"、 "梳理这个项目能解决什么业务问题"或要求建立 business-solution.md 等场景。
Harness Engineering 第一阶段第二步:深度分析项目代码,填充业务解决方案、架构、约定、技术决策和质量标准等 docs/ 知识库内容。 在 harness-step1-create-agents-md 创建好目录骨架之后使用。当用户说"填充文档内容"、 "完善 docs/ 文件"、"让文档有实质内容"、"分析项目写架构文档"、"写 ARCHITECTURE.md"、 "写技术决策文档"、"从业务视角理解项目"、"完善 business-solution.md"时,立即使用此 skill。 前置条件:项目中已有 AGENTS.md 和 docs/ 目录骨架(由 harness-step1 创建)。
Developer implementation guide for building hierarchical (folded) memory into an Agent. Three-layer architecture where recent turns stay detailed, older content compresses into episodes, and the oldest distills into durable semantic facts. Use when compact-memory-implementation is not retaining enough, or when agents need to recall decisions from many sessions ago.
Design and implement a layered, configurable permission/safety system for agent tools. Use this skill when building an agent that needs to control which tool calls are auto-allowed, which require user confirmation, and which are denied — especially when the system must be configurable across multiple scopes (project/user/enterprise) and extensible via hooks. Triggers on: "权限系统", "工具安全", "tool permission", "permission system", "tool safety", "allow/deny rules", "hook system", "构建安全机制".
Define agent tools using the fail-closed design pattern — unified name/schema/security/execution in one class, with three-layer execution (validate → permission → call). Use this skill whenever the user wants to define a new agent tool, add permission or validation logic to an existing tool, or asks about 'build a tool', '定义一个工具', 'create a tool for X', '工具定义'. Framework-agnostic: works with hermes-agent, LangChain, or any Python agent framework.
Build LangChain (Python) tools using Claude Code's fail-closed design pattern — unified name/schema/security/execution in one class, with automatic three-layer execution (validate → permission → call). Use this skill whenever the user wants to define a new LangChain tool, add permission or validation logic to an existing tool, set up the ClaudeStyleTool base class in a project, or asks about "build_tool", "Claude Code style tool", "工具定义", or "langchain tool with permissions". Also trigger when the user says "create a tool for X" or "定义一个工具" in a LangChain Python project context, even without mentioning Claude Code explicitly.
| name | storybrand-messaging-framework |
| description | Use StoryBrand for "clarify my message", "rewrite my homepage", "create a BrandScript", "what is my one-liner", or "fix my CTA". |
| license | Skill distillation for personal/educational use. Do not reproduce source passages verbatim. |
Use this skill to apply Donald Miller's StoryBrand SB7 framework to brand messaging, website copy, fundraising appeals, product positioning, sales pages, and marketing assets. The skill turns a confusing offer into a clear customer-centered story: the customer is the hero, the brand is the guide, the offer solves a real problem, and the next action is obvious.
This is a messaging-clarity skill. It does not validate whether a market exists, set paid-media budgets, or replace customer research.
Invoke this skill when the user asks:
Clear messaging beats clever messaging. The user must leave with copy that quickly answers: what is being offered, how it improves the customer's life, and what the customer should do next.
| Workflow | User question pattern | Inputs | Steps | Output | Should be subskill? |
|---|---|---|---|---|---|
| BrandScript creation | "Apply StoryBrand to my business" | Offer, customer, problem, proof, desired action | Fill all seven SB7 elements | Complete BrandScript | No — primary workflow |
| Website grunt test | "Review my homepage" | Existing copy or URL text | Test clarity, hierarchy, CTA, stakes, success | Rewrite and priority fixes | No — applies the same SB7 sequence |
| One-liner creation | "What is my pitch?" | Customer, problem, solution, result | Problem + solution + result | One-liner variants | No — narrow asset from SB7 |
| CTA and funnel design | "What should the CTA be?" | Buying stage, friction, trust level | Direct and transitional CTA mapping | CTA set and placement | No — Dimension 5 application |
| Asset rewrite | "Rewrite this email/ad/page" | Draft copy, audience, goal | Reframe customer as hero and brand as guide | Revised copy | No — channel-specific application |
Architecture decision: Keep this as a single-file skill. StoryBrand is one tightly coupled SB7 messaging workflow; BrandScripts, website reviews, one-liners, CTAs, and rewrites all reuse the same seven dimensions and usually share the same output assets. Splitting these into subskills would make routing heavier without improving decision quality.
Rule: The customer is the hero, not the brand.
Key questions:
Decision criteria:
Warning signals:
Agent instruction: Name the customer's concrete want before writing any brand copy. If the user provides many audiences or goals, ask them to pick the primary buyer for this pass.
Rule: Customers buy relief from internal frustration, not only solutions to external problems.
Key questions:
Decision criteria:
Warning signals:
Agent instruction: Diagnose all three problem levels and choose the one most likely to move the customer. Do not stop at feature-level pain points.
Rule: The brand must be the guide, not a competing hero.
Key questions:
Decision criteria:
Warning signals:
Agent instruction: Write one empathy line and one authority line. If proof is missing, mark it as a gap and suggest what evidence to collect.
Rule: A confused buyer does not move. A guide gives a simple path.
Key questions:
Decision criteria:
Warning signals:
Agent instruction: Produce a process plan for action and, when trust is low, an agreement plan that names guarantees, standards, or commitments.
Rule: Customers do not act unless challenged to act.
Key questions:
Decision criteria:
Warning signals:
Agent instruction: Always output both direct and transitional CTAs unless the channel only permits one.
Rule: Stakes make action meaningful, but fearmongering breaks trust.
Key questions:
Decision criteria:
Warning signals:
Agent instruction: Add one concise stakes statement, then quickly move to the success outcome.
Rule: The brand must paint the customer's successful future.
Key questions:
Decision criteria:
Warning signals:
Agent instruction: End major copy outputs with a before/after transformation and an aspirational identity statement.
Use this structure:
We help [customer] who struggle with [problem] get [solution] so they can [success].
For a complete messaging request, respond with:
## StoryBrand Diagnosis
- Customer:
- Primary desire:
- Main problem:
- Current clarity issue:
## BrandScript
1. Character:
2. Problem:
- External:
- Internal:
- Philosophical:
- Villain:
3. Guide:
- Empathy:
- Authority:
4. Plan:
5. Calls to action:
- Direct:
- Transitional:
6. Failure avoided:
7. Success:
## Copy Assets
- One-liner:
- Tagline options:
- Website hero:
- CTA set:
## Priority Fixes
1. ...
2. ...
3. ...
For a narrow rewrite, respond with:
## Revised Copy
...
## Why This Works
- Customer-as-hero shift:
- Problem clarity:
- CTA improvement:
## Remaining Gaps
- Proof needed:
- Customer decision needed:
When making substantive StoryBrand-method claims, cite the quote files if the user asks for sources or if the answer is a formal audit.
Quote files:
quotes/main-framework-quotes.md — SB7 rules, clarity, guide positioning, plan, CTA, stakes, transformation.quotes/storybrand-principles-quotes.md — broader StoryBrand principles and implementation reminders.Anchor mapping:
main-framework-quotes.md: #words-sell-things, #brain-drawn-to-clarity, #story-greatest-weapon, #customer-is-hero, #customer-looks-for-guide, #companies-sell-external, #trust-guide-with-plan, #call-to-action-required, #avoid-tragic-ending, #buying-transformation, #if-you-confuse-you-lose, #grunt-teststorybrand-principles-quotes.md: #story-organizes-information, #brain-survive-and-thrive, #story-makes-music, #think-different-lesson, #hero-in-a-hole, #three-levels-problems, #guide-positioning, #tidal-fatal-mistake, #story-gap-power, #conflict-gets-attention, #villain-focus, #plan-removes-confusion, #two-types-cta, #whats-at-stake, #aspirational-identity, #one-liner-formula, #website-hierarchyCitation format:
> "Author's exact words here."
>
> - [*Building a StoryBrand*, cited excerpt](https://github.com/simbajigege/book2skills/blob/main/skills/storybrand-messaging-framework/quotes/main-framework-quotes.md#customer-is-hero)
Use only exact quote text from the quote files. If no exact quote fits, cite the closest anchor and state that the analysis is a paraphrased application.